Inkling Models by Thinking Machines Lab

Thinking Machines LabApache 2.0Open source
Thinking Machines Lab releases · 2 in the last 12 monthsChangelog →
2 models2026Up to 1M ctxFrom $1.00/1M input

Last refreshed 2026-10-05. Next refresh: weekly.

Details

LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models2
Released2026
Max context1M

Capabilities

VisionAll models
MultimodalAll models
ReasoningAll models
JSON / Tool useAll models

About

Inkling is Thinking Machines Lab's open-weight general-purpose multimodal model family. Its initial 975B-total-parameter Mixture-of-Experts model accepts text, image, and audio inputs and produces text output with a 1M-token context window and controllable thinking effort.

Decision facts

Best fit
vision and multimodal workreasoningJSON / Tool use
Capability starting point
Inkling-Small with reasoning, JSON / Tool use, and multimodal inputs
Lowest tracked input
Inkling · $1.00/1M · Baseten API
Closest related family
360Zhinao

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs reasoning, JSON / Tool use, and multimodal inputs.

2026-07reasoningJSON / Tool usemultimodal inputs
InklingCurrent

Use when the workload needs 1M context, reasoning, and JSON / Tool use.

2026-071M contextreasoningJSON / Tool use

Release Timeline

1 release group
2026-07
2 current
Inkling
1M contextreasoningJSON / Tool use
Current
Inkling-Small
reasoningJSON / Tool usemultimodal inputs
Current

Specifications(2 models)

Inkling model specifications comparison
ModelReleasedContextParametersVisionMultimodalReasoningJSON / Tool use
Inkling-Small2026-07—276B (12B activated)YesYesYesYes
Inkling2026-071M975B total, 41B activeYesYesYesYes

Available From(3 providers)

Pricing

Inkling model pricing by provider
ModelProviderInput / 1MOutput / 1MType
InklingBaseten API$1$4.05Serverless
InklingOpenRouter$1$4.05Serverless
InklingTinker$1.87$4.68Provisioned